Abstract
This paper describes our submission for the SemEval-2019 Suggestion Mining task. A simple Convolutional Neural Network (CNN) classifier with contextual word representations from a pre-trained language model was used for sentence classification. The model is trained using tri-training, a semi-supervised bootstrapping mechanism for labelling unseen data. Tri-training proved to be an effective technique to accommodate domain shift for cross-domain suggestion mining (Subtask B) where there is no hand labelled training data. For in-domain evaluation (Subtask A), we use the same technique to augment the training set. Our system ranks thirteenth in Subtask A with an F1-score of 68.07 and third in Subtask B with an F1-score of 81.94.- Anthology ID:
- S19-2225
- Volume:
- Proceedings of the 13th International Workshop on Semantic Evaluation
- Month:
- June
- Year:
- 2019
- Address:
- Minneapolis, Minnesota, USA
- Editors:
- Jonathan May, Ekaterina Shutova, Aurelie Herbelot, Xiaodan Zhu, Marianna Apidianaki, Saif M. Mohammad
- Venue:
- SemEval
- SIG:
- SIGLEX
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 1282–1286
- Language:
- URL:
- https://aclanthology.org/S19-2225
- DOI:
- 10.18653/v1/S19-2225
- Cite (ACL):
- Sai Prasanna and Sri Ananda Seelan. 2019. Zoho at SemEval-2019 Task 9: Semi-supervised Domain Adaptation using Tri-training for Suggestion Mining. In Proceedings of the 13th International Workshop on Semantic Evaluation, pages 1282–1286, Minneapolis, Minnesota, USA. Association for Computational Linguistics.
- Cite (Informal):
- Zoho at SemEval-2019 Task 9: Semi-supervised Domain Adaptation using Tri-training for Suggestion Mining (Prasanna & Seelan, SemEval 2019)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-1/S19-2225.pdf